extend fuzzer to wide char types, integer parsing and all formats

fuzz/from_chars.cc

@@ -1,38 +1,205 @@
 #include "fast_float/fast_float.h"
 #include <fuzzer/FuzzedDataProvider.h>
+#include <cstdint>
+#include <cstdio>
+#include <cstdlib>
+#include <cstring>
 #include <string>
 #include <system_error>
+#include <type_traits>
+#include <vector>
+
+#if defined(__has_include)
+#if __has_include(<charconv>) && __cplusplus >= 201703L
+#include <charconv>
+#define FASTFLOAT_FUZZ_CHARCONV 1
+#endif
+#endif
+
+static void fail(char const *check) {
+  fprintf(stderr, "fast_float fuzz failure: %s\n", check);
+  abort();
+}
 
 fast_float::chars_format arbitrary_format(FuzzedDataProvider &fdp) {
   using fast_float::chars_format;
-  switch (fdp.ConsumeIntegralInRange<int>(0, 3)) {
+  chars_format format;
+  switch (fdp.ConsumeIntegralInRange<int>(0, 7)) {
   case 0:
-    return chars_format::scientific;
+    format = chars_format::scientific;
     break;
   case 1:
-    return chars_format::fixed;
+    format = chars_format::fixed;
     break;
   case 2:
-    return chars_format::fixed;
+    format = chars_format::json;
+    break;
+  case 3:
+    format = chars_format::json_or_infnan;
+    break;
+  case 4:
+    format = chars_format::fortran;
+    break;
+  case 5:
+    format = chars_format::javascript;
+    break;
+  case 6:
+    format = chars_format::javascript_sloppy;
+    break;
+  default:
+    format = chars_format::general;
     break;
   }
-  return chars_format::general;
+  if (fdp.ConsumeBool()) {
+    format = format | chars_format::allow_leading_plus;
+  }
+  if (fdp.ConsumeBool()) {
+    format = format | chars_format::skip_white_space;
+  }
+  return format;
+}
+
+template <typename T> uint64_t bits_of(T value) {
+  uint64_t bits = 0;
+  memcpy(&bits, &value, sizeof(T));
+  return bits;
+}
+
+// The same ASCII text must parse identically for every character type: same
+// error code, same number of consumed code units, bit-identical value.
+template <typename UC>
+void check_widened(std::string const &input,
+                   fast_float::from_chars_result_t<char> expected,
+                   double expected_value, fast_float::chars_format format) {
+  std::vector<UC> wide;
+  wide.reserve(input.size());
+  for (char c : input) {
+    wide.push_back(UC(static_cast<unsigned char>(c)));
+  }
+  double value = 0.0;
+  auto result = fast_float::from_chars(wide.data(), wide.data() + wide.size(),
+                                       value, format);
+  if (result.ec != expected.ec ||
+      (result.ptr - wide.data()) != (expected.ptr - input.data())) {
+    fail("wide result disagrees with char result");
+  }
+  if (expected.ec == std::errc() && bits_of(value) != bits_of(expected_value)) {
+    fail("wide value disagrees with char value");
+  }
+}
+
+// Every number format accepted by the library is pure ASCII, so a successful
+// parse must never consume a code unit >= 0x80. A violation means some helper
+// inspected only the low byte of a wide code unit (the bug behind #391).
+// The generated sequences keep an ASCII low byte but take hostile high bits:
+// top-bit-set units (near the minimum of a signed wchar_t, the shape behind
+// #422), sign-extended negative units (the shape behind #395), and non-ASCII
+// code points whose low byte is an ASCII digit (the shape behind #391).
+template <typename UC>
+void check_arbitrary_units(FuzzedDataProvider &fdp,
+                           fast_float::chars_format format) {
+  using unsigned_uc = typename std::make_unsigned<UC>::type;
+  size_t count = fdp.ConsumeIntegralInRange<size_t>(0, 64);
+  std::vector<UC> units;
+  units.reserve(count);
+  for (size_t i = 0; i < count; ++i) {
+    unsigned_uc unit = fdp.ConsumeIntegral<uint8_t>();
+    switch (fdp.ConsumeIntegralInRange<int>(0, 4)) {
+    case 0: // top bit set: near the minimum value when UC is signed
+      unit = unsigned_uc(unit | (unsigned_uc(1) << (sizeof(UC) * 8 - 1)));
+      break;
+    case 1: // all high bits set: a small negative value when UC is signed
+      unit = unsigned_uc(unit | ~unsigned_uc(0xFF));
+      break;
+    case 2: // arbitrary high byte: a non-ASCII code point, ASCII low byte
+      unit = unsigned_uc(
+          unit | unsigned_uc(unsigned_uc(fdp.ConsumeIntegral<uint8_t>()) << 8));
+      break;
+    default: // plain ASCII unit
+      break;
+    }
+    units.push_back(UC(unit));
+  }
+  if (units.empty()) {
+    return;
+  }
+  UC const *begin = units.data();
+  UC const *end = begin + units.size();
+
+  double as_double = 0.0;
+  auto result = fast_float::from_chars(begin, end, as_double, format);
+  if (result.ec == std::errc()) {
+    for (UC const *p = begin; p != result.ptr; ++p) {
+      if (static_cast<unsigned_uc>(*p) >= 0x80) {
+        fail("float parse consumed a non-ASCII code unit");
+      }
+    }
+  }
+  uint16_t as_uint16 = 0;
+  auto int_result = fast_float::from_chars(begin, end, as_uint16);
+  if (int_result.ec == std::errc()) {
+    for (UC const *p = begin; p != int_result.ptr; ++p) {
+      if (static_cast<unsigned_uc>(*p) >= 0x80) {
+        fail("integer parse consumed a non-ASCII code unit");
+      }
+    }
+  }
+}
+
+// fast_float's integer parsing is specified to match std::from_chars.
+template <typename T> void check_int(std::string const &input, int base) {
+  T value{};
+  auto result = fast_float::from_chars(
+      input.data(), input.data() + input.size(), value, base);
+#ifdef FASTFLOAT_FUZZ_CHARCONV
+  T expected{};
+  auto std_result = std::from_chars(input.data(), input.data() + input.size(),
+                                    expected, base);
+  if (result.ec != std_result.ec || result.ptr != std_result.ptr) {
+    fail("integer result disagrees with std::from_chars");
+  }
+  if (result.ec == std::errc() && value != expected) {
+    fail("integer value disagrees with std::from_chars");
+  }
+#else
+  static_cast<void>(result);
+#endif
+}
+
+template <typename T>
+void check_int_all_bases(std::string const &input, int base) {
+  check_int<T>(input, 10);
+  check_int<T>(input, base);
 }
 
 extern "C" int LLVMFuzzerTestOneInput(uint8_t const *data, size_t size) {
   FuzzedDataProvider fdp(data, size);
   fast_float::chars_format format = arbitrary_format(fdp);
-  double result_d = 0.0;
+  int base = fdp.ConsumeIntegralInRange<int>(2, 36);
+
   std::string input_d = fdp.ConsumeRandomLengthString(128);
-  auto answer = fast_float::from_chars(
+  double result_d = 0.0;
+  auto answer_d = fast_float::from_chars(
       input_d.data(), input_d.data() + input_d.size(), result_d, format);
-  std::string input_f = fdp.ConsumeRandomLengthString(128);
   float result_f = 0.0;
-  answer = fast_float::from_chars(
+  fast_float::from_chars(input_d.data(), input_d.data() + input_d.size(),
-      input_f.data(), input_f.data() + input_f.size(), result_f, format);
+                         result_f, format);
-  int result_i = 0;
+  check_widened<wchar_t>(input_d, answer_d, result_d, format);
+  check_widened<char16_t>(input_d, answer_d, result_d, format);
+  check_widened<char32_t>(input_d, answer_d, result_d, format);
+
   std::string input_i = fdp.ConsumeRandomLengthString(128);
-  answer = fast_float::from_chars(input_i.data(),
+  check_int_all_bases<uint8_t>(input_i, base);
-                                  input_i.data() + input_i.size(), result_i);
+  check_int_all_bases<int8_t>(input_i, base);
+  check_int_all_bases<uint16_t>(input_i, base);
+  check_int_all_bases<int16_t>(input_i, base);
+  check_int_all_bases<uint32_t>(input_i, base);
+  check_int_all_bases<int32_t>(input_i, base);
+  check_int_all_bases<uint64_t>(input_i, base);
+  check_int_all_bases<int64_t>(input_i, base);
+
+  check_arbitrary_units<wchar_t>(fdp, format);
+  check_arbitrary_units<char16_t>(fdp, format);
+  check_arbitrary_units<char32_t>(fdp, format);
   return 0;
 }